EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Implicit neural representation for medical image reconstruction

Yanjie Zhu iD, Yuanyuan Liu, Yihang Zhang, Dong Liang iD

Physics in Medicine & Biology · 22.06.2025 · 70 (12) · 12TR01

DOI: 10.1088/1361-6560/addfa5 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Physics in Medicine & Biology, online erschienen am 11.06.2025. Verfasst von Yanjie Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's …. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Diagnostic Imaging, Neural Networks, Computer. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Shenzhen Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical image reconstruction aims to generate high-quality images from incompletely sampled raw sensor data, which poses an ill-posed inverse problem. Traditional iterative reconstruction methods rely on prior information to empirically construct regularization terms, a process that is not trivial. While deep learning-based supervised reconstruction has made significant progress in improving image quality, it requires large-scale training data, which is difficult to obtain in medical imaging. Recently, implicit neural representation (INR) has emerged as a promising approach, offering a flexible and continuous representation of images by modeling the underlying signal as a function of spatial coordinates. This allows INR to capture fine details and complex structures more effectively than conventional discrete methods. This paper provides a comprehensive review of INR-based medical image reconstruction techniques, highlighting its growing impact on the field. The benefits of INR in both image and measurement domains are presented, and its advantages, limitations, and future research directions are discussed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedDiagnostic ImagingNeural Networks, ComputerHumans

Stichwörter der Autor:innen

implicit neural representationmedical image reconstructionregularizations

Autor:innen und Institutionen

  • Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.
  • College of Pharmacy and Bioengineering, Chongqing University of Technology, Chongqing, People's Republic of China.
  • Research Center for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, People's Republic of China.

ORCID-Profile: Yanjie Zhu, Dong Liang

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Shenzhen Science and Technology Program
  • Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province

Zitieren

APA

Zhu, Y., Liu, Y., Zhang, Y., & Liang, D. (2025). Implicit neural representation for medical image reconstruction. Physics in Medicine & Biology, 70(12), 12TR01. https://doi.org/10.1088/1361-6560/addfa5

Vancouver

Zhu Y, Liu Y, Zhang Y, Liang D. Implicit neural representation for medical image reconstruction. Physics in Medicine & Biology. 2025;70(12):12TR01. doi:10.1088/1361-6560/addfa5

BibTeX
@article{Zhu2025,
  author = {Zhu, Yanjie and Liu, Yuanyuan and Zhang, Yihang and Liang, Dong},
  title = {Implicit neural representation for medical image reconstruction},
  journal = {Physics in Medicine & Biology},
  year = {2025},
  volume = {70},
  number = {12},
  pages = {12TR01},
  doi = {10.1088/1361-6560/addfa5}
}
Kostenlos starten →